9 citations · 14 across the 16 of their papers we have counts for
16 papers
Scaling E-Commerce Attribute Extraction with Parallel Decoding
Nikhita Vedula, Dushyanta Dhyani, Bryan Wang +1
Customers rely on specific product attributes to compare products and make purchasing decisions, but e-commerce catalogs are messy and unstructured, making it difficult to identify…
Text-to-Distribution Prediction with Quantile Tokens and Neighbor Context
Yilun Zhu, Yuan Zhuang, Nikhita Vedula +6
Many applications of LLM-based text regression require predicting a full conditional distribution rather than a single point value. We study distributional regression under empiric…
CodeV: Code with Images for Faithful Visual Reasoning via Tool-Aware Policy Optimization
Xinhai Hou, Shaoyuan Xu, Manan Biyani +4
Agentic vision-language models are increasingly trained to "think with images" by calling image operations. However, we show that high final-answer accuracy often hides unfaithful…
AlignFlow: Improving Flow-based Generative Models with Semi-Discrete Optimal Transport
Lingkai Kong, Molei Tao, Yang Liu +4
Flow-based Generative Models (FGMs) effectively transform noise into complex data distributions. Incorporating Optimal Transport (OT) to couple noise and data during FGM training h…
CORRECT: COndensed eRror RECognition via knowledge Transfer in multi-agent systems
Yifan Yu, Moyan Li, Shaoyuan Xu +4
Multi-agent systems (MAS) are increasingly capable of tackling complex real-world tasks, yet their reliance on inter-agent coordination, tool use, and long-horizon reasoning makes…
QID: Efficient Query-Informed ViTs in Data-Scarce Regimes for OCR-free Visual Document Understanding
Binh M. Le, Shaoyuan Xu, Jinmiao Fu +6
In Visual Document Understanding (VDU) tasks, fine-tuning a pre-trained Vision-Language Model (VLM) with new datasets often falls short in optimizing the vision encoder to identify…
Temporal-Consistent Video Restoration with Pre-trained Diffusion Models
Hengkang Wang, Yang Liu, Huidong Liu +5
Video restoration (VR) aims to recover high-quality videos from degraded ones. Although recent zero-shot VR methods using pre-trained diffusion models (DMs) show good promise, they…
Cost-Effective Hallucination Detection for LLMs
Simon Valentin, Jinmiao Fu, Gianluca Detommaso +3
Large language models (LLMs) can be prone to hallucinations - generating unreliable outputs that are unfaithful to their inputs, external facts or internally inconsistent. In this…
Q-Tuning: Queue-based Prompt Tuning for Lifelong Few-shot Language Learning
Yanhui Guo, Shaoyuan Xu, Jinmiao Fu +3
This paper introduces \textbf{Q-tuning}, a novel approach for continual prompt tuning that enables the lifelong learning of a pre-trained language model. When learning a new task,…
Hierarchical Conditional Semi-Paired Image-to-Image Translation For Multi-Task Image Defect Correction On Shopping Websites
Moyan Li, Jinmiao Fu, Shaoyuan Xu +3
On shopping websites, product images of low quality negatively affect customer experience. Although there are plenty of work in detecting images with different defects, few efforts…
KD-FixMatch: Knowledge Distillation Siamese Neural Networks
Chien-Chih Wang, Shaoyuan Xu, Jinmiao Fu +2
Semi-supervised learning (SSL) has become a crucial approach in deep learning as a way to address the challenge of limited labeled data. The success of deep neural networks heavily…
AdaSelection: Accelerating Deep Learning Training through Data Subsampling
Minghe Zhang, Chaosheng Dong, Jinmiao Fu +8
In this paper, we introduce AdaSelection, an adaptive sub-sampling method to identify the most informative sub-samples within each minibatch to speed up the training of large-scale…
Promptify: Text-to-Image Generation through Interactive Prompt Exploration with Large Language Models
Stephen Brade, Bryan Wang, Mauricio Sousa +2
Text-to-image generative models have demonstrated remarkable capabilities in generating high-quality images based on textual prompts. However, crafting prompts that accurately capt…
CMA-CLIP: Cross-Modality Attention CLIP for Image-Text Classification
Huidong Liu, Shaoyuan Xu, Jinmiao Fu +5
Modern Web systems such as social media and e-commerce contain rich contents expressed in images and text. Leveraging information from multi-modalities can improve the performance…
Demonstration of PerformanceNet: A Convolutional Neural Network Model for Score-to-Audio Music Generation
Yu-Hua Chen, Bryan Wang, Yi-Hsuan Yang
We present in this paper PerformacnceNet, a neural network model we proposed recently to achieve score-to-audio music generation. The model learns to convert a music piece from the…
PerformanceNet: Score-to-Audio Music Generation with Multi-Band Convolutional Residual Network
Bryan Wang, Yi-Hsuan Yang
Music creation is typically composed of two parts: composing the musical score, and then performing the score with instruments to make sounds. While recent work has made much progr…